Global Interpretability via Automated Preprocessing: A Framework Inspired by Psychiatric Questionnaires
This work provides a more interpretable and accurate method for clinicians to predict future symptom severity from questionnaire data, which is an incremental improvement for psychiatric prognosis.
This paper addresses the challenge of predicting future symptom severity from psychiatric questionnaires, where traditional methods struggle with context sensitivity and weak predictive power. The authors propose REFINE, a two-stage method that uses a nonlinear preprocessing module to stabilize item values, followed by a linear model for prediction, outperforming other interpretable approaches in both psychiatric and non-psychiatric longitudinal prediction tasks.
Psychiatric questionnaires are highly context sensitive and often only weakly predict subsequent symptom severity, which makes the prognostic relationship difficult to learn. Although flexible nonlinear models can improve predictive accuracy, their limited interpretability can erode clinical trust. In fields such as imaging and omics, investigators commonly address visit- and instrument-specific artifacts by extracting stable signal through preprocessing and then fitting an interpretable linear model. We adopt the same strategy for questionnaire data by decoupling preprocessing from prediction: we restrict nonlinear capacity to a baseline preprocessing module that estimates stable item values, and then learn a linear mapping from these stabilized baseline items to future severity. We refer to this two-stage method as REFINE (Redundancy-Exploiting Follow-up-Informed Nonlinear Enhancement), which concentrates nonlinearity in preprocessing while keeping the prognostic relationship transparently linear and therefore globally interpretable through a coefficient matrix, rather than through post hoc local attributions. In experiments, REFINE outperforms other interpretable approaches while preserving clear global attribution of prognostic factors across psychiatric and non-psychiatric longitudinal prediction tasks.